© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Attention Out - 32k
    9. 3-ATT_32K-OAI
    11. 3643
    Prev
    Next
    INDEX
    Explanations

    mentions of routine activities or processes, particularly in a security or administrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-attn-out-SAEs/v5_32k_layer_3
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.3.hook_attn_out
    Hook Layer
    3
    Architecture
    standard
    Context Size
    64
    Dataset
    Skylion007/openwebtext
    Activation Function
    topk
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    227
    +0.10
    0.4%
    403
    +0.09
    0.4%
    745
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    403
    +0.10
    0.01
    450
    +0.09
    0.01
    227
    +0.09
    0.01
    Negative Logits
     stakes
    -0.78
    ortium
    -0.69
     interven
    -0.67
     hoard
    -0.64
     Samar
    -0.63
     Pau
    -0.63
    etheus
    -0.63
     Bern
    -0.60
     Alpha
    -0.60
     Ky
    -0.60
    POSITIVE LOGITS
     routine
    0.75
    Repeat
    0.74
    lication
    0.72
    tenance
    0.72
    rences
    0.72
     Schedule
    0.70
    pmwiki
    0.70
    ItemImage
    0.69
    Reviewer
    0.69
    icides
    0.68
    Activations Density 0.087%

    No Known Activations